© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163512
    Prev
    Next
    INDEX
    Explanations

    linear fit

    np_acts-logits-general · gemini-2.5-flash-lite

    is to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     आहेत
    0.49
    oluminescence
    0.49
    សម្
    0.47
    鹉
    0.46
     முய
    0.45
    ndes
    0.45
    髏
    0.44
     బంగ
    0.44
    ză
    0.43
    ज
    0.43
    POSITIVE LOGITS
     commuter
    0.52
     ferries
    0.51
    caster
    0.45
     viviendas
    0.45
     baddies
    0.45
     উদ্বাস্তু
    0.44
     roads
    0.44
     ferry
    0.44
     camper
    0.43
     apartments
    0.43
    Activations Density 0.000%

    No Known Activations